Courseiva

AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure

Which Azure AI service extracts key information (like invoice numbers, dates, and amounts) from structured documents like forms and invoices?

⚠ Common exam trap

Many candidates confuse Azure AI Vision's OCR capability with Document Intelligence's specialized form extraction, assuming that general OCR is sufficient for structured data extraction, but Document Intelligence provides prebuilt models and key-value pair extraction that Vision lacks.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

Azure AI Document Intelligence

Azure AI Document Intelligence (formerly Form Recognizer) is the correct service because it is specifically designed to extract structured data such as invoice numbers, dates, and amounts from forms and invoices. It uses prebuilt models for invoices and receipts, along with custom model training, to perform optical character recognition (OCR) and key-value pair extraction from structured documents.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Azure AI Language

    Why it's wrong here

    Azure AI Language is built for text analytics, such as sentiment classification, key phrase extraction, and question answering, rather than for interpreting scanned business documents. Its entity recognition might identify a date or organization in plain text, but it does not process the spatial layout, column boundaries, or field-to-value relationships found in invoices. Furthermore, it expects clean text input, not a multi-page PDF or JPEG with tables, so it would fail to deliver structured extraction from the original document.

  • Azure AI Document Intelligence

    Why this is correct

    Azure AI Document Intelligence (formerly Form Recognizer) is the appropriate service because it uses prebuilt and custom models to extract key-value pairs, tables, and text from invoices, receipts, and forms. It analyzes the physical arrangement of text, recognizes the semantic meaning of fields, and outputs a normalized JSON schema with confidence scores for each extracted value. This matches the requirement to extract structured data directly from a document image without writing custom parsing logic.

  • Azure AI Vision

    Why it's wrong here

    Azure AI Vision's Read API can perform optical character recognition and return text with bounding boxes, but it does not identify document-level semantics like an invoice's vendor, total, or line items. It treats everything as loosely located text and lacks the prebuilt models and layout reasoning needed to group text into keys, values, and tables. Document Intelligence builds on OCR and adds specialized extraction to produce structured JSON, which is why Vision is not sufficient for this task.

  • Azure AI Translator

    Why it's wrong here

    Azure AI Translator converts text between languages using neural machine translation, but it does not inspect document layout or semantic fields. When given an invoice, it would translate the textual content while ignoring the relationship between labels and values, such as "Ship To" and a billing address. Extracting structured data from invoices requires a service that understands key-value pairs and table structure, not a language translation engine.

About these practice questions

This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.